Medical Reasoning on MedBul5
55.5AccuracyOurs
Evaluation results
| Method | Links | |
|---|---|---|
| OursModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 55.5 | |
| m1kModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 51.4 | |
| Middle PerplexityModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 50.6 | |
| RandomModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 49.8 | |
| S2LModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 47.4 | |
| Embedding DiversityModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 47.2 | |
| LearnabilityModel=Qwen2.5-7B-Instruct, Training=Finetuning, Sample size=1000 examples2026.06 | 42.9 |